39 lines
1.2 KiB
YAML

version: "3.8"
networks:
argus-sys-net:
external: true
services:
metric-gpu-node:
image: ${NODE_GPU_BUNDLE_IMAGE_TAG:-argus-sys-metric-test-node-bundle-gpu:${PKG_VERSION}}
container_name: argus-metric-gpu-node-swarm
hostname: ${GPU_NODE_HOSTNAME}
restart: unless-stopped
privileged: true
runtime: nvidia
environment:
- TZ=Asia/Shanghai
- DEBIAN_FRONTEND=noninteractive
- MASTER_ENDPOINT=${MASTER_ENDPOINT:-http://master.argus.com:3000}
# Fluent Bit / 日志上报目标(固定域名)
- ES_HOST=es.log.argus.com
- ES_PORT=9200
- ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
- ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
- AGENT_ENV=${AGENT_ENV}
- AGENT_USER=${AGENT_USER}
- AGENT_INSTANCE=${AGENT_INSTANCE}
- NVIDIA_VISIBLE_DEVICES=all
- NVIDIA_DRIVER_CAPABILITIES=compute,utility
- GPU_MODE=gpu
networks:
argus-sys-net:
aliases:
- ${AGENT_INSTANCE}.node.argus.com
volumes:
- ../private/argus/agent:/private/argus/agent
- ../logs/infer:/logs/infer
- ../logs/train:/logs/train
command: ["sleep", "infinity"]